github-template-ai-agents
llms.txt2 starsChanged 9 days agoMITView on GitHub
Opinionated GitHub template for teams who want reproducible, multi-agent software delivery with shared instructions, quality gates, and low-context-rot workflows. Rule: AGENTS.md is the only place shared instructions live. Tool files extend or override; they never duplicate. This repository provides a unified harness for AI coding agents with consistent workflows across multiple tools. It emphasizes quality gates, skill systems, and context discipline.
In this repository63 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/avoid-ai-writing/AGENTS.mdAGENTS.md
- .agents/skills/do-web-doc-resolver/AGENTS.mdAGENTS.md
- .agents/skills/skill-evaluator/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- accessibility-auditorSkill
- agent-browserSkill
- agentic-abstentionSkill
- agents-mdSkill
- api-design-firstSkill
- architecture-diagramSkill
- avoid-ai-writingSkill
- cicd-pipelineSkill
- cloudflare-worker-apiSkill
- codacySkill
- codeberg-apiSkill
- code-review-assistantSkill
- css-render-performanceSkill
- database-devopsSkill
- debuggerSkill
- delegateSkill
- dependency-upgradesSkill
- dist-channel-selectionSkill
- docs-hookSkill
- document-rendering-and-locatorsSkill
- dogfoodSkill
- dora-reportSkill
- do-web-doc-resolverSkill
- durable-objectsSkill
- eu-ai-act-complianceSkill
- git-github-workflowSkill
- goap-agentSkill
- implementerSkill
- intent-classifierSkill
- iterative-refinementSkill
- jules-delegatorSkill
- learnSkill
- lifecycle-managementSkill
- local-context-sanitizationSkill
- memory-contextSkill
- migration-refactoringSkill
- nested-build-isolationSkill
- privacy-firstSkill
- progressive-deliverySkill
- pwa-offline-syncSkill
- reader-ui-uxSkill
- readme-best-practicesSkill
- secrets-managementSkill
- secure-invite-and-accessSkill
- security-code-auditorSkill
- shell-script-qualitySkill
- skill-creatorSkill
- skill-evaluatorSkill
- static-analysisSkill
- testing-strategySkill
- test-runnerSkill
- triz-solverSkill
- turso-dbSkill
- The first 60 shown.
The file
We split this llms.txt into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Atomic Commits: Every commit must address exactly one concern and follow Conventional Commits.
- Distinctive: line 21
Context Isolation: Use sub-agents to isolate complex tasks and prevent context rot.
≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
# GitHub Template AI Agents > Opinionated GitHub template for teams who want reproducible, multi-agent software delivery with shared instructions, quality gates, and low-context-rot workflows. **Rule:** `AGENTS.md` is the only place shared instructions live. Tool files extend or override; they never duplicate. This repository provides a unified harness for AI coding agents with consistent workflows across multiple tools. It emphasizes quality gates, skill systems, and context discipline. ## Key Files & Directories - [AGENTS.md](AGENTS.md): Single source of truth for all AI coding agents in this repository. - [.agents/skills/](.agents/skills/): Canonical location for reusable knowledge modules (skills). - [plans/](plans/): Directory for Architecture Decision Records (ADRs) and GOAP execution plans. - [agents-docs/](agents-docs/): Comprehensive documentation for the harness, workflows, and skills. - [scripts/](scripts/): Automation scripts for setup, validation, and maintenance. - [VERSION](VERSION): Single source of truth for the project version. ## Core Conventions - **Atomic Commits**: Every commit must address exactly one concern and follow Conventional Commits. - **GOAP Planning**: Goal-Oriented Action Planning is used to decompose tasks into atomic steps. - **Quality Gates**: Mandatory validation scripts (linting, testing) must pass before any commit. - **Context Isolation**: Use sub-agents to isolate complex tasks and prevent context rot. ## Essential Skills - [goap-agent](.agents/skills/goap-agent/): Coordinate complex workflows using goal-oriented planning. - [git-github-workflow](.agents/skills/git-github-workflow/): Orchestrate the full git-to-merge lifecycle with CI monitoring and auto-fix. - [shell-script-quality](.agents/skills/shell-script-quality/): Ensure high-quality shell scripts with ShellCheck and BATS. ## Optional - [Full Skill Catalog](agents-docs/AVAILABLE_SKILLS.md): Reference for all available agent skills. - [Architecture Overview](agents-docs/HARNESS.md): Deep dive into the harness architecture. - [Workflow Guide](agents-docs/WORKFLOW.md): Detailed explanation of atomic commits and development phases.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.